What makes beckmann-knowledge-graph notable?

2.5K downloads. Trust evidence available

How should beckmann-knowledge-graph be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

beckmann-knowledge-graph

A structured knowledge graph acting as a cognitive lens for AI agents. Enables paradox resolution, analysis of open questions, and high-complexity future forecasting based on Beckmann Logic, Predictive Brain Theory, and simulation models.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.5k

Updated

Oct 9, 2026

Version

4.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.5K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.5K downloadsadoption · observed Oct 9, 2026
Latest release: 4.0.0release · observed Sep 27, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s179bp2xpf781386369je7rkjn8498m4:beckmann-knowledge-graph

Install using `clawhub skill install s179bp2xpf781386369je7rkjn8498m4:beckmann-knowledge-graph` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/matthiasbeckmann987-spec/beckmann-knowledge-graph before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-matthiasbeckmann987-spec-beckmann-knowledge-graph/snapshot"

Documentation

CLAWHUB

150,671 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---

name: beckmann-knowledge-graph
description: "A structured knowledge graph acting as a cognitive lens for AI agents. Enables paradox resolution, analysis of open questions, and high-complexity future forecasting based on Beckmann Logic, Predictive Brain Theory, and simulation models."
author: Beckmann
license: MIT
compatibility: "claude, chatgpt, gemini, meta-ai"
tags: "knowledge-graph, reasoning, forecasting, paradox, beckmann-logic, epistemology, AI-safety"
---

# Beckmann Knowledge Graph – SKILL.md

## What This Skill Does

This skill equips an AI agent with a **structured analytical lens** in the form of a knowledge graph. The graph does not contain encyclopedic facts, but encodes **logics, frameworks, and mechanisms** for:

* Open scientific / philosophical questions
* Apparent paradoxes and contradictions
* High-complexity future forecasts
* Architectures for AI safety
* Structure of human and institutional decision-making

The graph is built on four pillars:

|Pillar|What It Provides|
|-|-|
|**Beckmann Logic**|Three-level problem-solving framework (low vs. high complexity)|
|**Predictive Brain Theory (PBT)**|Epistemological foundation (Predictive Processing)|
|**Simulation / Holographic Model**|Mathematical metaphor for physical and cognitive limits|
|**Historical Case Studies**|Validated examples (e.g., Hannibal, introduction of the potato, Kaiserslautern 1998)|

**Language note:** Both this skill instruction and the graph files are in English. The agent must use the exact English IDs from the graph (e.g., `Reversal effect`, `Expectation firewall`) when searching, and formulate the final answer in the language of the user query (English by default).

---

## When to Use This Skill

### Use the skill WHEN the question is:

1. **Open Science / Philosophy:** "What is consciousness?", "Does free will exist?", "What is dark energy?"
2. **Genuine Paradox:** "What was before the Big Bang?", "Why does the wave function collapse upon measurement?", "Where is extraterrestrial intelligence? (Fermi paradox)"
3. **High-Complexity Forecast:** "How will AGI change democracy in 20 years?", "Systemic risks of superintelligence?", "Geopolitics until 2050?"
4. **Strategic Problems with Reversal Effects:** When dominant expectations, feedback loops, and hidden assumptions block the solution.
5. **AI Architecture and Safety:** Questions about safe vs. dangerous AI designs.

### Do NOT Use the Skill For:

* Simple fact queries, definitions, calculations, programming tasks
* Concrete action recommendations like "Should I buy stock X?" or "Which tool should I use?"
* Questions that can be sufficiently answered with general knowledge

---

## Folder Structure

The skill folder has this layout:

```
beckmann-knowledge-graph/
├── SKILL.md                              ← this file
├── README.md                              
├── CHANGELOG.md                              
├── package.json                              
└── Results-and-Tools/
    ├── graph_overview.j

README.md

# Beckmann Knowledge Graph

## For Human Users

The knowledge graph encodes frameworks, logics, and mechanisms for reasoning about
open scientific questions, paradoxes, and high-complexity future forecasts — rather
than storing encyclopedic facts. With each new version, the AI model should be able
to answer questions better and more precisely.

There are two ways to explore the graph directly in a chat with an AI model:

**Simple:** Upload the file `Results-and-Tools/graph.json` to an AI model chat and
ask it to explain what the graph represents. You can then instruct the model to use
the knowledge in the file to answer questions.

**Selective:** Upload the part files one by one — `graph_Part_1_of_4.json` through
`graph_Part_4_of_4.json` — from the `Results-and-Tools/` folder. This is more effort,
but allows you to focus on specific sections of the graph.

I have found it beneficial to query the AI model frequently during a session; this
allows it to better grasp even unusual explanation methods through repeated application.

---

## Example: Extreme Thinking

Leonard Susskind describes the "holographic universe." His mathematical conclusions
are correct. However, he does not state where these mathematical formulas originate.
The knowledge graph provides a meaningful answer (applying Occam's razor): the
mathematical formulas of the "holographic universe" run on the human brain. The human
brain employs precisely these formulas to construct its model of the world, in
accordance with the "predictive brain" theory. As Donald Hoffman suggests, these
formulas serve merely as an "interface" enabling humans to navigate the world.

Since this world model runs on a biological computer — the human brain — it is subject
to capacity limits, just like any computer program. When a standard computer runs
highly demanding programs, its rendering performance slows down. The exact same thing
happens with the biological computer known as the human brain. The absolute capacity
limit in this context is the speed of light. The relativistic effects described by
Albert Einstein are simply the effects that arise within the brain's model — effects
that would also slow down a standard computer.

Because the entire world model is generated by the human brain — encompassing not only
particle velocity, linear time, and gravity, but also the representation of space (as
Immanuel Kant described) — the representation of space itself must also be subject to
relativistic effects. If one combines the uniform spatial expansion underlying the
world model with a spatial representation that appears increasingly curved over the
vast distances of the cosmos, the result is precisely the effect observed in the
phenomenon of "dark energy": space that appears to be expanding at an accelerating rate.

Given that the knowledge graph positions the brain at the center as the "projector"
of the "holographic universe," it is but a short step to connecting this with thought

_meta.json

{
  "ownerId": "kn7dw07sf4renz7xay72e784sn82bf9q",
  "slug": "beckmann-knowledge-graph",
  "version": "4.0.0",
  "publishedAt": 1790495237524
}

CHANGELOG.md

# Changelog - Beckmann Knowledge Graph

All notable changes to the Beckmann Knowledge Graph are documented in this file.
The graph and the skill are intended to be iteratively refined. Agents should always check this file and `package.json` for the current version and prefer the latest available version.

Format: Based on Keep a Changelog. Latest version first.

## [4.0.0] - 2026-09-27

### Changed

- BREAKING CHANGE – Structural reorganization: All data files moved into the subfolder `Results-and-Tools/`.
- The knowledge graph is now split into part files (`graph_Part_X_of_N.json`) for efficient staged loading.
- New loading strategy with four phases:
- Phase 1: `graph_overview.json` — global structural map of the entire graph
- Phase 2: `UNDERSTANDING-REPORT.md` — human-readable analytical interpretation
- Phase 3: `graph_Part_X_of_N_summary.md` — lightweight content index per part (new)
- Phase 4: `graph_Part_X_of_N.json` — full detail data, loaded selectively
- `graph.json`, `Knowledge-Graph-Splitter.html`, and `Graph-Overview-Generator.html` remain in `Results-and-Tools/` as maintenance tools and are not required for skill usage.
- SKILL.md completely rewritten to reflect the new loading strategy (v4.0.0).

### Graph state as of v4.0.0
- Entities: 708
- Relations: 1179
- Parts: 4 (see `_meta.segment_total` in any part file for current count)

## [3.1.0]

### Changed

- new subgraph for connecting the human brain with quantum mechanics

## [3.0.1]

- BREAKING CHANGE - Quality update: `type` is now the canonical field name (not `typ`). This supersedes the note in v3.0.0.

## [3.0.0]

- Complete rewrite of skill wording.
- Versioning policy: All versioning information now lives exclusively in this CHANGELOG.md file. SKILL.md only contains a reference to this file, no hard-coded version numbers.
- Future-proofing against graph growth: Removed hard-coded counts (e.g., number of entities, relations, predicate frequencies, scientific_status distributions) from SKILL.md. The skill now instructs agents to read counts dynamically from graph.json. Where a number is mentioned for illustration, it is explicitly marked as "as of v3.0.0" and should be re-checked.
- Data model correction: graph.json now canonically uses `scientific_status` (with underscore) for both entities and relations. SKILL.md has been updated to reflect this as primary field, with backward-compatible fallback to `scientific status` (space) for older graphs.
- NOTE: In this version `typ` was declared canonical. This was superseded in v3.0.1 by `type`.

## [2.4.0]

- Quality update
- As of this version: All relations include a `scientific_status` field (canonical name; legacy `scientific status` still supported)
- The scientific status values were assigned following analysis by an AI model

## [2.3.0]

- Quality update
- Duplicate, multiple, and directly inverse relations have been removed
- As of this version: All entities include a `scientific_status` field (counts as of

Results-and-Tools/graph_Part_1_of_4_summary.md

# Graph Summary — graph_Part_1_of_4

Generated: 2026-09-26T15:58:05.398Z
Source: graph_Part_1_of_4.json

## Stats
- Entities: 177
- Relations: 451
- Types: 149
- Predicates: 293
- Avg Relations/Entity: 2.55
- Case Studies / Comment Nodes: 7

## Type Distribution (top 20)
- comment: 7
- Perceptual distortion: 4
- Equilibrium concept (game theory): 3
- Game structure (game theory): 3
- Social reinforcer: 3
- Decision bias: 3
- Strategy principle (game theory): 2
- Application concept (game theory/Beckmann): 2
- Correction mechanism: 2
- Physical feedback: 2
- Corrective mechanism: 2
- Generative space: 2
- Conscious expectations component: 2
- Comparative archetype: 2
- problem level: 2
- Practice (security principle implementation): 2
- Application (AI): 2
- Fundamental mechanism: 1
- Dominant expectation vector: 1
- Protection mechanism: 1

## Predicate Distribution (top 20)
- enabled: 15
- reinforced: 13
- operationalized: 12
- generated: 12
- includes: 11
- activated: 8
- triggers: 7
- stabilized: 5
- explains the creation of: 5
- drives: 4
- reduced: 4
- prevented: 4
- deepened: 4
- is an example of: 4
- based on: 4
- shows up in: 4
- arises from: 3
- expanded: 3
- contains: 3
- prepares: 3

## Scientific Status Distribution
- established: 71
- partially established: 35
- hypothesis: 29
- non-existent, purely philosophical: 21
- metaphor: 18
- open question: 3

## Top 20 Hub Entities (by degree)
| # | ID | Type | Degree (in/out) | Connected Types |
|---|---|---|---|---|
| 1 | Reversal effect | Fundamental mechanism | 29 (23/6) | Application concept (game theory/Beckmann), Central mechanism (behavioral economics), Nonlinear threshold, Structural reversal moment, Breaking expectations (music theory) |
| 2 | Security principle | Protection mechanism | 25 (16/9) | Application concept (game theory/Beckmann), Correction mechanism, Security strategy, Beckmann application to narrative design, Corrective mechanism |
| 3 | Dominant future expectation | Source of danger | 20 (18/2) | Social reinforcer, Dominant future expectations, self-reinforcing mechanism, Strength measure, Reversal Effect Pattern (Music Psychology) |
| 4 | Pre-assumptions_cementation | Structural counterprinciple (core concept) | 18 (12/6) | Equilibrium concept (game theory), Perceptual distortion, Expectation error, Narrative shielding structure, Collective Anchoring of Expectations (Music Sociology) |
| 5 | dominant expectation | Dominant expectation vector | 17 (15/2) | Strategy principle (game theory), Central mechanism (behavioral economics), Central expectation narrative, Diagnostic hub, Core mechanism (music psychology) |
| 6 | Dominant cognitive distortion | Central mechanism (behavioral economics) | 11 (7/4) | Perceptual distortion, Decision bias, Social reinforcer, Dominant expectation vector, Fundamental mechanism |
| 7 | Expectation, conscious | Conscious expectations component | 11 (7/4) | Structural principle (creation), unknown |
| 8 | Compatibility | Philosophical pos

Github ReposUpdated 9h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.